演算式決策與學習
Algorithmic Decision & Learning
| 節 | 週二 |
|---|---|
5 13:20–14:10 | 演算式決策與學習 MB312（光復） 3 節連堂 |
6 14:20–15:10 | |
7 15:30–16:20 |
* 根據陽明交大上課時間表所列
As an emerging and active interdisciplinary research area, with contributions from theoretical computer science, economics, networking, artificial intelligence, operations research, and discrete mathematics, “algorithmic game theory” and “learning in multiagent systems” are focused on the analysis of equilibria such as efficiency of equilibria and complexity of computing equilibria, learning to reach equilibria in repeated games, or learning for design mechanism. In addition, we give a perspective on machine learning that treats “fairness” as a central concern. We will briefly review machine learning in a way that highlights ethical challenges, particularly, bias and even discrimination, with some approaches to mitigate these problems.
教師未提供此項資料
無備註
教師未提供此項資料
Evaluation and Grading Policy: Homework: 4 assignments (60%) Final Presentation: reading and presentation (40%)
Introduction: Algorithmic decision
1. Introduction and Overview: Algorithms, Game theory and equilibria
- 講授：
- 9
Price of anarchy
1. Selfish routing in networks and other congestion games: Nash equilibria 2. Randomized load balancing games 3. Network design with selfish agents 4. Other games
- 講授：
- 12
Computing equilibria & Learning in multiagent systems
1. Existence and complexity of computing equilibria 2. Online learning/optimization 3. Convergence of natural game play
- 講授：
- 9
Multiagent systems
- 講授：
- 3
Fairness and bias in machine learning
1. Classification by supervised learning 2. Formal non-discrimination criteria 3. Relationships between criteria
- 講授：
- 9
Final presentation
- 其他：
- 6
| 週次 | 主題 |
|---|---|
| 第 1 週 | Introduction and overview |
| 第 2 週 | Game theory and equilibria |
| 第 3 週 | Efficiency of equilibria |
| 第 4 週 | Price of anarchy |
| 第 5 週 | Price of anarchy |
| 第 6 週 | Price of anarchy |
| 第 7 週 | Price of anarchy |
| 第 8 週 | Computing equilibria |
| 第 9 週 | Online learning |
| 第 10 週 | Learning in games |
| 第 11 週 | Multiagent systems |
| 第 12 週 | Fairness and bias in machine learning |
| 第 13 週 | Fairness and bias in machine learning |
| 第 14 週 | Fairness and bias in machine learning |
| 第 15 週 | Presentations |
| 第 16 週 | Presentations |
Algorithmic Game Theory, edited by Noam Nisan, Tim Roughgarden, and Vijay V. Vazirani. 2007 Fairness and Machine Learning, by Solon Barocas, Moritz Hardt, and Arvind Narayanan. 2021 Handbook of Computational Social Choice. 2016 Multiagent Systems: Algorithmic, Game-Theoretic, and Logical Foundations, by Yoav Shohan and Kevin Leyton–Brown. 2009 References: Conference papers mainly from ACM EC, WINE, AAMAS, SAGT, STOC, FOCS, SODA, AAAI, etc. Journal papers mainly from GEB, IJGT, ACM TEAC, AIJ, JAIR, etc.
- 地點
- TBD
- 時間
- By appointment
- 聯絡方式
- poanch@gmail.com